Copertina

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yanzuo, Liu, Zhibo, Yuan, Yuanyuan, Hu, Sihang, Li, Tianxiang, Wang, Shuai
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Targeted Bit-Flip Attacks on LLM-Based Agents
di: Wang, Jialai, et al.
Pubblicazione: (2026)

A Semi Black-Box Adversarial Bit-Flip Attack with Limited DNN Model Information
di: Ghavami, Behnam, et al.
Pubblicazione: (2024)

FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning
di: Khalil, Khurram, et al.
Pubblicazione: (2025)

FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models
di: Nazari, Najmeh, et al.
Pubblicazione: (2025)

DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
di: Velčický, Patrik, et al.
Pubblicazione: (2024)

Verification of Bit-Flip Attacks against Quantized Neural Networks
di: Zhang, Yedi, et al.
Pubblicazione: (2025)

FlipAttack: Jailbreak LLMs via Flipping
di: Liu, Yue, et al.
Pubblicazione: (2024)

GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs
di: Das, Sanjay, et al.
Pubblicazione: (2024)

Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models
di: Liu, Deng, et al.
Pubblicazione: (2026)

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
di: Liu, Zesen, et al.
Pubblicazione: (2025)

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
di: Yan, Xiaobei, et al.
Pubblicazione: (2025)

Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
di: Kummer, Lorenz, et al.
Pubblicazione: (2023)

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
di: Yan, Lu, et al.
Pubblicazione: (2025)

Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
di: Liu, Qingyu, et al.
Pubblicazione: (2026)

SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
di: Xu, Haotian, et al.
Pubblicazione: (2025)

Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)
di: Zhao, Taibiao, et al.
Pubblicazione: (2026)

Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers
di: Chen, Simin, et al.
Pubblicazione: (2025)

TFL: Targeted Bit-Flip Attack on Large Language Model
di: Guo, Jingkai, et al.
Pubblicazione: (2026)

Side-Channel Attacks on Open vSwitch
di: Kim, Daewoo, et al.
Pubblicazione: (2026)

Attacks on Approximate Caches in Text-to-Image Diffusion Models
di: Sun, Desen, et al.
Pubblicazione: (2025)

TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments
di: Liu, Ziyu, et al.
Pubblicazione: (2024)

Bit-Flipping Attack Exploration and Countermeasure in 5G Network
di: Kim, Joon, et al.
Pubblicazione: (2025)

ObfusBFA: A Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks
di: Yan, Xiaobei, et al.
Pubblicazione: (2025)

NetDiffuser: Deceiving DNN-Based Network Attack Detection Systems with Diffusion-Generated Adversarial Traffic
di: Kumar, Pratyay, et al.
Pubblicazione: (2026)

Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors
di: Borjigin, Ailiya, et al.
Pubblicazione: (2026)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
di: Zhang, Shuoming, et al.
Pubblicazione: (2025)

Invisible Hands: Gray-Box Bit Flip Attack for Steering LLMs Without Knowledge of Gradients, Data, and Weights
di: Almalky, Abeer Matar A., et al.
Pubblicazione: (2025)

CAN-Trace Attack: Exploit CAN Messages to Uncover Driving Trajectories
di: Lin, Xiaojie, et al.
Pubblicazione: (2025)

BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks
di: Lee, Hanyong, et al.
Pubblicazione: (2025)

SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models
di: Guo, Jingkai, et al.
Pubblicazione: (2025)

Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation
di: Zhang, Wenhui, et al.
Pubblicazione: (2025)

DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
di: Zhou, Ranyang, et al.
Pubblicazione: (2023)

BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs
di: Karamat, Muhammad Zeeshan, et al.
Pubblicazione: (2025)

3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models
di: Yin, Jianyao, et al.
Pubblicazione: (2025)

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior
di: Lian, Zhuotao, et al.
Pubblicazione: (2025)

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
di: Li, Yanzeng, et al.
Pubblicazione: (2025)

Impactful Bit-Flip Search on Full-precision Models
di: Benedek, Nadav, et al.
Pubblicazione: (2024)

LoopTrap: Termination Poisoning Attacks on LLM Agents
di: Xu, Huiyu, et al.
Pubblicazione: (2026)

LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models
di: Tahmasivand, Ahmad, et al.
Pubblicazione: (2025)

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models
di: Ding, Zikang, et al.
Pubblicazione: (2026)